In recent years we have witnessed an explosion of research, development, and applications of Deep Learning. The main objective of this course is to provide a wide overview of the current state of this area and to focus on a few, carefully selected topics, covering them in depth by studying and presenting most relevant papers, and doing own research on these selected topics. This research will have a form of producing new experimental results, testing new algorithms or theories and documenting findings in scientific reports. The best reports can be submitted to conferences or published as research papers.
During the course students will work (in small teams) on selected topics/problems, performing experiments on GPU-computers, reporting on their progress during weekly meetings. Each team will have to summarize their work in a final presentation and a project report.
Outcome:
During the course students will:
gain an overall picture of the recent developments in Deep Learning,
identify some promising research directions,
gain some hands-on research experience, including studying related papers, identifying research problems, inventing solutions of these problems, verifying their ideas by experimenting and documenting findings in a scientific style,
learn to work together is small research teams,
learn to prepare and give presentations,
learn to write scientific reports.